Add new SentenceTransformer model.

.gitattributes

@@ -30,3 +30,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+unigram.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+pytorch_model.bin filter=lfs diff=lfs merge=lfs -text

1_Pooling/config.json

@@ -0,0 +1,7 @@
+{
+  "word_embedding_dimension": 384,
+  "pooling_mode_cls_token": false,
+  "pooling_mode_mean_tokens": true,
+  "pooling_mode_max_tokens": false,
+  "pooling_mode_mean_sqrt_len_tokens": false
+}

README.md

@@ -0,0 +1,129 @@
+---
+pipeline_tag: sentence-similarity
+tags:
+- sentence-transformers
+- feature-extraction
+- sentence-similarity
+- transformers
+
+---
+
+# {MODEL_NAME}
+
+This is a [sentence-transformers](https://www.SBERT.net) model: It maps sentences & paragraphs to a 384 dimensional dense vector space and can be used for tasks like clustering or semantic search.
+
+<!--- Describe your model here -->
+
+## Usage (Sentence-Transformers)
+
+Using this model becomes easy when you have [sentence-transformers](https://www.SBERT.net) installed:
+
+```
+pip install -U sentence-transformers
+```
+
+Then you can use the model like this:
+
+```python
+from sentence_transformers import SentenceTransformer
+sentences = ["This is an example sentence", "Each sentence is converted"]
+
+model = SentenceTransformer('{MODEL_NAME}')
+embeddings = model.encode(sentences)
+print(embeddings)
+```
+
+
+
+## Usage (HuggingFace Transformers)
+Without [sentence-transformers](https://www.SBERT.net), you can use the model like this: First, you pass your input through the transformer model, then you have to apply the right pooling-operation on-top of the contextualized word embeddings.
+
+```python
+from transformers import AutoTokenizer, AutoModel
+import torch
+
+
+#Mean Pooling - Take attention mask into account for correct averaging
+def mean_pooling(model_output, attention_mask):
+    token_embeddings = model_output[0] #First element of model_output contains all token embeddings
+    input_mask_expanded = attention_mask.unsqueeze(-1).expand(token_embeddings.size()).float()
+    return torch.sum(token_embeddings * input_mask_expanded, 1) / torch.clamp(input_mask_expanded.sum(1), min=1e-9)
+
+
+# Sentences we want sentence embeddings for
+sentences = ['This is an example sentence', 'Each sentence is converted']
+
+# Load model from HuggingFace Hub
+tokenizer = AutoTokenizer.from_pretrained('{MODEL_NAME}')
+model = AutoModel.from_pretrained('{MODEL_NAME}')
+
+# Tokenize sentences
+encoded_input = tokenizer(sentences, padding=True, truncation=True, return_tensors='pt')
+
+# Compute token embeddings
+with torch.no_grad():
+    model_output = model(**encoded_input)
+
+# Perform pooling. In this case, mean pooling.
+sentence_embeddings = mean_pooling(model_output, encoded_input['attention_mask'])
+
+print("Sentence embeddings:")
+print(sentence_embeddings)
+```
+
+
+
+## Evaluation Results
+
+<!--- Describe how your model was evaluated -->
+
+For an automated evaluation of this model, see the *Sentence Embeddings Benchmark*: [https://seb.sbert.net](https://seb.sbert.net?model_name={MODEL_NAME})
+
+
+## Training
+The model was trained with the parameters:
+
+**DataLoader**:
+
+`torch.utils.data.dataloader.DataLoader` of length 2166 with parameters:
+```
+{'batch_size': 128, 'sampler': 'torch.utils.data.sampler.RandomSampler', 'batch_sampler': 'torch.utils.data.sampler.BatchSampler'}
+```
+
+**Loss**:
+
+`sentence_transformers.losses.MultipleNegativesRankingLoss.MultipleNegativesRankingLoss` with parameters:
+  ```
+  {'scale': 20.0, 'similarity_fct': 'cos_sim'}
+  ```
+
+Parameters of the fit()-Method:
+```
+{
+    "epochs": 10,
+    "evaluation_steps": 216,
+    "evaluator": "sentence_transformers.evaluation.EmbeddingSimilarityEvaluator.EmbeddingSimilarityEvaluator",
+    "max_grad_norm": 1,
+    "optimizer_class": "<class 'torch.optim.adamw.AdamW'>",
+    "optimizer_params": {
+        "lr": 1e-06
+    },
+    "scheduler": "WarmupLinear",
+    "steps_per_epoch": null,
+    "warmup_steps": 2166,
+    "weight_decay": 0.01
+}
+```
+
+
+## Full Model Architecture
+```
+SentenceTransformer(
+  (0): Transformer({'max_seq_length': 128, 'do_lower_case': False}) with Transformer model: BertModel 
+  (1): Pooling({'word_embedding_dimension': 384, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False})
+)
+```
+
+## Citing & Authors
+
+<!--- Describe where people can find more information -->

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "models/ocnli-cnsd-multi-MiniLM-v2/",
+  "architectures": [
+    "BertModel"
+  ],
+  "attention_probs_dropout_prob": 0.1,
+  "classifier_dropout": null,
+  "gradient_checkpointing": false,
+  "hidden_act": "gelu",
+  "hidden_dropout_prob": 0.1,
+  "hidden_size": 384,
+  "initializer_range": 0.02,
+  "intermediate_size": 1536,
+  "layer_norm_eps": 1e-12,
+  "max_position_embeddings": 512,
+  "model_type": "bert",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 12,
+  "pad_token_id": 0,
+  "position_embedding_type": "absolute",
+  "torch_dtype": "float32",
+  "transformers_version": "4.21.1",
+  "type_vocab_size": 2,
+  "use_cache": true,
+  "vocab_size": 250037
+}

config_sentence_transformers.json

@@ -0,0 +1,7 @@
+{
+  "__version__": {
+    "sentence_transformers": "2.0.0",
+    "transformers": "4.7.0",
+    "pytorch": "1.9.0+cu102"
+  }
+}

eval/similarity_evaluation_sts-dev_results.csv

@@ -0,0 +1,27 @@
+epoch,steps,cosine_pearson,cosine_spearman,euclidean_pearson,euclidean_spearman,manhattan_pearson,manhattan_spearman,dot_pearson,dot_spearman
+0,216,0.8420036101577641,0.8477162107433588,0.8106965591576962,0.8197193414495011,0.8092609853788798,0.8179553411674493,0.7519864808899812,0.7683260519465919
+0,432,0.8432265936136198,0.8483197014011108,0.8101926464070567,0.8195105193229808,0.8088002504514279,0.8178336707955142,0.7549897264280511,0.7714115354031804
+0,648,0.8434345875217619,0.8482651041535004,0.8089602546769898,0.8186237755489868,0.8075672403936979,0.8169398536370678,0.7547271215808249,0.7714713019056929
+0,864,0.841563052174142,0.8466586879616355,0.8061854312834752,0.8155760104650602,0.8050221966401055,0.81420357349539,0.7524086876443303,0.7695845866190143
+0,1080,0.840230142733557,0.8448760714801591,0.8041759077478932,0.8134109659186369,0.8030426976035514,0.8121704893947274,0.7505250411417995,0.7680108492313532
+0,1296,0.8380605379479314,0.8424778411488563,0.8014610340574587,0.8104476502016563,0.8003918710447693,0.8094873487887786,0.7477365986807009,0.7650037663370429
+0,1512,0.8376050393895086,0.8424599545199523,0.7996646572060943,0.8089466844464998,0.7984183105808597,0.8076428907633734,0.7465113350704993,0.7625443619135865
+0,1728,0.8361534651882101,0.8410234838670125,0.7970869905726814,0.8059571775388996,0.7959217125946396,0.8049193849503605,0.7430154396959366,0.7600955273544253
+0,1944,0.8313883603926658,0.8360067332610265,0.7910333888212726,0.8006052272056177,0.7902262687161201,0.799594049431932,0.7366869047533736,0.7535218699233902
+0,2160,0.827235455326802,0.8320015987055898,0.7891203197566264,0.7980345555713426,0.7886810385810262,0.7973118645055062,0.735358221690519,0.750991384502041
+0,-1,0.8271390695731811,0.8318854763479596,0.7890627399177387,0.797960311930541,0.7886143808634505,0.7972159753397546,0.7352887047940263,0.7507858130002387
+0,216,0.8411487843824286,0.8471253374297658,0.8106198720523566,0.8195390424212514,0.8091869387162447,0.8178213716677323,0.7503583049382798,0.7666419720212299
+0,432,0.8414797568536371,0.8473193390435743,0.8107387096436172,0.81964881240095,0.8093124524759123,0.8180574317798547,0.7510447955130188,0.7674027583994651
+0,648,0.8419278217382398,0.8476730379066542,0.8108296026119635,0.8197674982456907,0.8094082076401231,0.8180509474131725,0.7519958712741737,0.768305186885048
+0,864,0.8424022408104653,0.8480086456615539,0.8108375660687243,0.8198357700708442,0.8094117294221671,0.818091405475969,0.7530686001231317,0.7694163909534381
+0,1080,0.8428292301211644,0.8482082855538595,0.8107186124632874,0.8198796151558223,0.8092799846091845,0.8181619602091681,0.7543208572432004,0.7706462863074403
+0,1296,0.8432072860356189,0.8483129298014214,0.810514497094325,0.8199485196441711,0.8090981923686018,0.8181567739736365,0.7554612720996471,0.771767485492661
+0,1512,0.8432884800123164,0.8481762340030274,0.8099578464895437,0.8195109488774277,0.8085581738244885,0.8177522186097962,0.7558723044936776,0.772553447025959
+0,1728,0.8431016207569118,0.8478487320395043,0.8091551871590602,0.8186812821067967,0.8077527817558212,0.8171157137028975,0.7557509793761882,0.7724219200798936
+0,1944,0.843000078208571,0.8477134256038226,0.8086256500788442,0.8181226485362433,0.8072662160745225,0.816605528171153,0.7556463363865691,0.7724639280512333
+0,2160,0.8429364841906399,0.8475202999475956,0.8080915119461467,0.8176306136310965,0.8067522189544144,0.8160559791992851,0.7557201174053868,0.7724887095307975
+0,-1,0.8429261427476151,0.8475312992326165,0.8080984155907812,0.817652580430085,0.8067576384161439,0.8160996622602396,0.7556737386454906,0.7724511857423662
+1,216,0.8425177003749148,0.8470659329167659,0.8078989364228251,0.8173012100290717,0.8065825193488042,0.8158453278286679,0.7551257172477217,0.7717541511733772
+1,432,0.8422631479234384,0.8467123898118666,0.8072056673608483,0.8165424295375284,0.8059439830734247,0.8151952321806387,0.7552834670030084,0.7718855101715042
+1,648,0.8418332208801085,0.8463782769598794,0.8065002062185747,0.8158357619098844,0.8053030031620603,0.8145536864613482,0.7547273079803445,0.77173195758822
+1,864,0.8416471304313258,0.8461856489048937,0.8059927638452845,0.8151941592896871,0.8048280341059416,0.8140796765247217,0.7546506823090642,0.771890422154738

modules.json

@@ -0,0 +1,14 @@
+[
+  {
+    "idx": 0,
+    "name": "0",
+    "path": "",
+    "type": "sentence_transformers.models.Transformer"
+  },
+  {
+    "idx": 1,
+    "name": "1",
+    "path": "1_Pooling",
+    "type": "sentence_transformers.models.Pooling"
+  }
+]

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:caa829c4756bb62e66a31398a54b2d84a6f97054b1656bd3c60d7f70b2ef6401
+size 470684465

sentence_bert_config.json

@@ -0,0 +1,4 @@
+{
+  "max_seq_length": 128,
+  "do_lower_case": false
+}

special_tokens_map.json

@@ -0,0 +1,15 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "eos_token": "</s>",
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "unk_token": "<unk>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b60b6b43406a48bf3638526314f3d232d97058bc93472ff2de930d43686fa441
+size 17082913

tokenizer_config.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": "<s>",
+  "cls_token": "<s>",
+  "do_lower_case": true,
+  "eos_token": "</s>",
+  "mask_token": {
+    "__type": "AddedToken",
+    "content": "<mask>",
+    "lstrip": true,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 512,
+  "name_or_path": "models/ocnli-cnsd-multi-MiniLM-v2/",
+  "pad_token": "<pad>",
+  "sep_token": "</s>",
+  "special_tokens_map_file": null,
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "BertTokenizer",
+  "unk_token": "<unk>"
+}

unigram.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71b44701d7efd054205115acfa6ef126c5d2f84bd3affe0c59e48163674d19a6
+size 14763234